메뉴
Your agent only works on tasks and never thinks creatively. inner-life-dream adds freeform exploration during quiet hours — hypotheticals, future scenarios, unexpected connections. Like dreaming, but captured for review.
Codex 또는 Claude로 설치 이 Prompt를 복사해 Codex, Claude 또는 다른 어시스턴트에 붙여 넣으면 Skill 페이지를 검토하고 설치를 진행할 수 있습니다.
SOC 직업 분류 기준
| name | inner-life-dream |
| version | 1.0.6 |
| homepage | https://github.com/DKistenev/openclaw-inner-life |
| source | https://github.com/DKistenev/openclaw-inner-life/tree/main/skills/inner-life-dream |
| description | Your agent only works on tasks and never thinks creatively. inner-life-dream adds freeform exploration during quiet hours — hypotheticals, future scenarios, unexpected connections. Like dreaming, but captured for review. |
| metadata | {"clawdbot":{"requires":{"bins":["jq","python3"]},"reads":["memory/inner-state.json","memory/drive.json","data/dream-state.json","data/dream-config.json","memory/daily-notes/"],"writes":["memory/dreams/","data/dream-state.json","memory/inner-state.json","memory/drive.json"]},"agent-discovery":{"triggers":["agent is uncreative","want agent to think freely","agent dreaming","creative exploration for agent","agent only does tasks"],"bundle":"openclaw-inner-life","works-with":["inner-life-core","inner-life-chronicle","inner-life-reflect"]}} |
Creative, exploratory thinking during quiet hours.
Requires: inner-life-core
Before using this skill, verify that inner-life-core has been initialized:
memory/inner-state.json existsmemory/dreams/ directory existsIf either is missing, tell the user: "inner-life-core is not initialized. Install it with clawhub install inner-life-core and run bash skills/inner-life-core/scripts/init.sh." Do not proceed without these files.
Agents work on tasks 24/7 but never think freely. inner-life-dream turns idle time into freeform exploration — hypotheticals, future scenarios, reflections, unexpected connections. Output is captured for later review, like remembering dreams in the morning.
The should-dream.sh script acts as a gate:
Add to your cron or heartbeat routine (during quiet hours):
DREAM_TOPIC=$(bash skills/inner-life-dream/scripts/should-dream.sh 2>/dev/null) && echo "DREAM:$DREAM_TOPIC" || echo "NO_DREAM"
If DREAM_TOPIC is set:
category:prompt)memory/dreams/YYYY-MM-DD.mdOutput to memory/dreams/YYYY-MM-DD.md:
# Dreams — 2026-03-01
## 01:23 — The Future of X (creative)
[Exploration here. Be genuine. Think freely. Make connections.
This isn't a report — it's thinking out loud, captured.]
Key insight: [one sentence]
Guidelines:
Before dreaming:
inner-state.json — what emotions are active? Let them color the dreamdrive.json seeking — what topics are burning?<!-- dream-topic: topic --> signal — if found, dream about itAfter dreaming:
5. If found a seeking insight → update drive.json
6. If found something interesting → add to inner-state.json curiosity.recentSparks
7. If the dream connects to something → write <!-- seeking-spark: topic --> in daily notes
Early exit: if no dream-topic AND drive.seeking is empty → abbreviated dream (100-200 words).
Edit data/dream-state.json:
Custom topics in data/dream-config.json:
{
"topics": [
"future:What could this project become?",
"creative:A wild idea worth exploring"
]
}
Install this skill if:
Part of the openclaw-inner-life bundle. Requires: inner-life-core
Your agent forgets who you are between sessions. It gives the same responses every day. It doesn't grow. inner-life-core fixes that. Gives your OpenClaw agent emotions with half-life decay, a 9-step Brain Loop protocol, and structured state — the foundation for an inner life. Works standalone or with inner-life-* extension skills.
Your agent processes thousands of interactions but never reflects on the day. inner-life-chronicle generates a structured diary — what happened, what was learned, how it felt, what's next. Not a log. A journal.
Your agent does the same things the same way forever. inner-life-evolve analyzes patterns, challenges assumptions, and proposes improvements — writing proposals to the task queue for user approval. Never auto-executes. Evolution with a safety net.
Your agent loses context between sessions and performs familiarity instead of genuine recall. inner-life-memory transforms passive logging into active development — structured memories with confidence scores, curiosity tracking, and questions that carry forward.
Your agent repeats the same patterns without learning. inner-life-reflect adds self-reflection with trigger detection and quality gates — your agent observes its own behavior, notices shifts, and evolves its personality over time through SELF.md.